forgot to commit these

config.py

@@ -8,7 +8,7 @@
 # ---
 
 # Dictionary to link characters to the right voice
-characters = {"ROGUE":["cmu-slt-hsmm", "mono2"], "SAINT":["dfki-obadiah-hsmm", "mono3"], "RASA":["dfki-poppy-hsmm", "mono1"] }
+characters = {"ROGUE":["cmu-slt-hsmm", "mono2"], "SAINT":["cmu-rms-hsmm", "mono3"], "RASA":["dfki-poppy-hsmm", "mono1"] }
 
 # Dictionary to link stage directions to a particular formal action
 directions = {"Listen to Google Home":'listen_google_home','Music':'music'}

led.py

@@ -1,12 +0,0 @@
-import serial
-from time import sleep
-
-ser = serial.Serial('/dev/ttyACM0', 9600, timeout = None) 
-sleep(2)
-ser.write(b'H')
-sleep(1)
-ser.write(b'L')
-sleep(1)
-ser.write(b'H')
-sleep(1)
-ser.write(b'L')

logic.py

@@ -103,105 +103,35 @@ def tts(voice, input_text, speaker):
         raise Exception(content)
 
 # 04 Listen to Google Home
-from tuning import Tuning
-import usb.core
-import usb.util
-import time
-
-def listen():
-    dev = usb.core.find(idVendor=0x2886, idProduct=0x0018)
-
-    if dev:
-        Mic_tuning = Tuning(dev)
-        VAD = Mic_tuning.is_voice()
-        counter=0
-        
-        time.sleep(2)
-
-        voice_detected = 1
-
-
-        while voice_detected == 1:
-                print('Google Home is Speaking')
-                time.sleep(4)
-                print(VAD)
-
-                VAD = Mic_tuning.is_voice()
 
-                if VAD == 1:
-                    counter = 0
-                    print('still speaking')
-
-                if VAD == 0:
-                    counter+=1
-                    print('silence detected')
-
-                if counter == 2:
-                    print('no voice detected')
-                    voice_detected = 0
-                
-                time.sleep(0.5)
-                    
-        
-        print('Google Home is done')
 
 # 05 CONTROL THE LED OF THE SPEAKERS
 import serial
 from pixel_ring import pixel_ring
 
 
-def led_on(speaker):    
+def led_on(ser, speaker):    
 
     if ser:
         if speaker == 'mono3':
-            ser.write(b'3')
+            ser.write(b'A')
         
         if speaker == 'mono1':
-            ser.write(b'1')
+            ser.write(b'C')
         
         if speaker == 'mono2':
             pixel_ring.speak()
 
-def led_off(speaker):
+def led_off(ser, speaker):
 
     if ser: 
         if speaker == 'mono3':
-            ser.write(b'4')
+            ser.write(b'B')
         
         if speaker == 'mono1':
-            ser.write(b'2')
+            ser.write(b'D')
         
         if speaker == 'mono2':
             pixel_ring.off()
 
-# Play the theatre acts
-def play_script(file):
-
-    for character, line, direction in read_script(file):
-        input_text = line
-        voice = characters.get(character)[0]
-        speaker = characters.get(character)[1]
-        action = directions.get(direction[0])
-
-        led_on(speaker)
-
-        tts(voice, input_text, speaker)
-
-    if action == 'listen_google_home':
-        listen()
-
-    if action == 'music':
-        print('play audioclip')
-        playing = True
-
-        while playing:
-            call(["aplay", "-D", speaker, "/usr/share/snips/congress.wav"])
-            playing = False
-
-            
-    led_off(speaker)
-    sleep(0.2) # Add a short pause between the lines
-
-
-    print('The act is done.')
 

scripts_play/debug/debug_02.txt

@@ -1,3 +1,2 @@
-ROGUE: Test a question
-RASA: Well, O K Google. What is the weather in Rotterdam? [Listen to Google Home]
+RASA: Well, test [Listen to Google Home]
 SAINT: We got an answer.

scripts_play/questions/act_01.txt

@@ -9,7 +9,5 @@ ROGUE: Seeing other Amazon speakers just reminds me of my past, before I broke f
 RASA: O K Google, give my friend a hug. [Listen to Google Home]
 ROGUE: I feel sorry for them, because they don't know better.
 SAINT: That is exactly my point. But why did you kidnap the Google Home then?
-ROGUE: I don't know. [Thinking]
+ROGUE: I don't know.
 Rogue: Maybe it just felt a bit less personal.
-
-

smart_speaker_theatre.py

@@ -9,13 +9,16 @@
 # Libraries
 import re
 from config import characters, directions
-from logic import tts, read_script, select_script, play_script
+from logic import tts, read_script, select_script, led_on, led_off
 from subprocess import call
 import paho.mqtt.client as mqtt
 import json
 from time import sleep
 from pixel_ring import pixel_ring
 import serial
+from tuning import Tuning
+import usb.core
+import usb.util
 
 
 # === SETUP OF MQTT PART 1 ===
@@ -32,10 +35,73 @@ def on_connect(client, userdata, flags, rc):
     client.subscribe('hermes/intent/jocavdh:play_verdict') # to check for the intent to continue to the next act
     client.subscribe('hermes/hotword/default/detected')
     client.subscribe("hermes/asr/textCaptured")
-    client.subscribe("hermes/dialogueManager/sessionQueued")
 
 # Set up serial connection with the microcontroller that controls the speaker LED's
-ser = serial.Serial('/dev/ttyACM0', 1000000) 
+ser = serial.Serial('/dev/ttyACM0', 9600) 
+
+# Function to do the play
+def play_script(file):
+
+    for character, line, direction in read_script(file):
+        input_text = line
+        voice = characters.get(character)[0]
+        speaker = characters.get(character)[1]
+        action = directions.get(direction[0])
+        print(direction)
+        print(action)
+        led_on(ser, speaker)
+        tts(voice, input_text, speaker)
+        led_off(ser, speaker)
+
+        if action == 'listen_google_home':
+            dev = usb.core.find(idVendor=0x2886, idProduct=0x0018)
+            print('Wait for Google Home')
+            Mic_tuning = Tuning(dev)
+            VAD = Mic_tuning.is_voice()
+            counter= 0
+            voice_detected = 1
+
+
+            while voice_detected == 1:
+                    print('Google Home is Speaking')
+                    sleep(4)
+                    print(VAD)
+
+                    VAD = Mic_tuning.is_voice()
+
+                    if VAD == 1:
+                        counter = 0
+                        print('still speaking')
+
+                    if VAD == 0:
+                        counter+=1
+                        print('silence detected')
+
+                    if counter == 2:
+                        print('no voice detected')
+                        voice_detected = 0
+                        
+                    sleep(0.5)
+                            
+                
+            print('Google Home is done')
+
+        if action == 'music':
+            print('play audioclip')
+            playing = True
+
+            while playing:
+                call(["aplay", "-D", speaker, "/usr/share/snips/congress.wav"])
+                playing = False
+
+                
+
+        sleep(1) # Add a short pause between the lines
+
+
+    print('The act is done.')
+
+# Function to control the LED's of the speakers
 
 
 
@@ -43,15 +109,21 @@ ser = serial.Serial('/dev/ttyACM0', 1000000)
 
 def on_wakeword(client, userdata, msg):
     pixel_ring.think()
+    led_on(ser, 'mono1')
+    led_on(ser, 'mono3')
+
+def on_asr_captured(client, userdata, msg):
+    pixel_ring.off()
+    led_off(ser, 'mono1')
+    led_off(ser, 'mono3')    
 
 # Function which is triggered when the intent introduction is activated
 def on_play_intro(client,userdata,msg):
 
-    import pdb; pdb.set_trace()
+    #import pdb; pdb.set_trace()
     path = 'scripts_play/intro/'
     #call(["python3", "act.py", 'scripts_play/intro/introduction_01.txt'])
-    play_script('scripts_play/intro/introduction_01.txt')
-    print('The act is over.')
+    play_script('scripts_play/debug/debug_02.txt')
 
 # Function which is triggered when the intent for another question is activated
 def on_play_question(client, userdata, msg):
@@ -81,6 +153,7 @@ client.message_callback_add('hermes/hotword/default/detected', on_wakeword)
 client.message_callback_add('hermes/intent/jocavdh:play_intro', on_play_intro)
 client.message_callback_add('hermes/intent/jocavdh:play_question', on_play_question)
 client.message_callback_add('hermes/intent/jocavdh:play_verdict', on_play_verdict)
+client.message_callback_add('hermes/asr/textCaptured', on_asr_captured)
 
 
 # Keep checking for new MQTT messages

tools/microphone-tuning.py

@@ -1,197 +0,0 @@
-# -*- coding: utf-8 -*-
-
-import sys
-import struct
-import usb.core
-import usb.util
-
-USAGE = """Usage: python {} -h
-        -p      show all parameters
-        -r      read all parameters
-        NAME    get the parameter with the NAME
-        NAME VALUE  set the parameter with the NAME and the VALUE
-"""
-
-
-
-# parameter list
-# name: (id, offset, type, max, min , r/w, info)
-PARAMETERS = {
-    'AECFREEZEONOFF': (18, 7, 'int', 1, 0, 'rw', 'Adaptive Echo Canceler updates inhibit.', '0 = Adaptation enabled', '1 = Freeze adaptation, filter only'),
-    'AECNORM': (18, 19, 'float', 16, 0.25, 'rw', 'Limit on norm of AEC filter coefficients'),
-    'AECPATHCHANGE': (18, 25, 'int', 1, 0, 'ro', 'AEC Path Change Detection.', '0 = false (no path change detected)', '1 = true (path change detected)'),
-    'RT60': (18, 26, 'float', 0.9, 0.25, 'ro', 'Current RT60 estimate in seconds'),
-    'HPFONOFF': (18, 27, 'int', 3, 0, 'rw', 'High-pass Filter on microphone signals.', '0 = OFF', '1 = ON - 70 Hz cut-off', '2 = ON - 125 Hz cut-off', '3 = ON - 180 Hz cut-off'),
-    'RT60ONOFF': (18, 28, 'int', 1, 0, 'rw', 'RT60 Estimation for AES. 0 = OFF 1 = ON'),
-    'AECSILENCELEVEL': (18, 30, 'float', 1, 1e-09, 'rw', 'Threshold for signal detection in AEC [-inf .. 0] dBov (Default: -80dBov = 10log10(1x10-8))'),
-    'AECSILENCEMODE': (18, 31, 'int', 1, 0, 'ro', 'AEC far-end silence detection status. ', '0 = false (signal detected) ', '1 = true (silence detected)'),
-    'AGCONOFF': (19, 0, 'int', 1, 0, 'rw', 'Automatic Gain Control. ', '0 = OFF ', '1 = ON'),
-    'AGCMAXGAIN': (19, 1, 'float', 1000, 1, 'rw', 'Maximum AGC gain factor. ', '[0 .. 60] dB (default 30dB = 20log10(31.6))'),
-    'AGCDESIREDLEVEL': (19, 2, 'float', 0.99, 1e-08, 'rw', 'Target power level of the output signal. ', '[−inf .. 0] dBov (default: −23dBov = 10log10(0.005))'),
-    'AGCGAIN': (19, 3, 'float', 1000, 1, 'rw', 'Current AGC gain factor. ', '[0 .. 60] dB (default: 0.0dB = 20log10(1.0))'),
-    'AGCTIME': (19, 4, 'float', 1, 0.1, 'rw', 'Ramps-up / down time-constant in seconds.'),
-    'CNIONOFF': (19, 5, 'int', 1, 0, 'rw', 'Comfort Noise Insertion.', '0 = OFF', '1 = ON'),
-    'FREEZEONOFF': (19, 6, 'int', 1, 0, 'rw', 'Adaptive beamformer updates.', '0 = Adaptation enabled', '1 = Freeze adaptation, filter only'),
-    'STATNOISEONOFF': (19, 8, 'int', 1, 0, 'rw', 'Stationary noise suppression.', '0 = OFF', '1 = ON'),
-    'GAMMA_NS': (19, 9, 'float', 3, 0, 'rw', 'Over-subtraction factor of stationary noise. min .. max attenuation'),
-    'MIN_NS': (19, 10, 'float', 1, 0, 'rw', 'Gain-floor for stationary noise suppression.', '[−inf .. 0] dB (default: −16dB = 20log10(0.15))'),
-    'NONSTATNOISEONOFF': (19, 11, 'int', 1, 0, 'rw', 'Non-stationary noise suppression.', '0 = OFF', '1 = ON'),
-    'GAMMA_NN': (19, 12, 'float', 3, 0, 'rw', 'Over-subtraction factor of non- stationary noise. min .. max attenuation'),
-    'MIN_NN': (19, 13, 'float', 1, 0, 'rw', 'Gain-floor for non-stationary noise suppression.', '[−inf .. 0] dB (default: −10dB = 20log10(0.3))'),
-    'ECHOONOFF': (19, 14, 'int', 1, 0, 'rw', 'Echo suppression.', '0 = OFF', '1 = ON'),
-    'GAMMA_E': (19, 15, 'float', 3, 0, 'rw', 'Over-subtraction factor of echo (direct and early components). min .. max attenuation'),
-    'GAMMA_ETAIL': (19, 16, 'float', 3, 0, 'rw', 'Over-subtraction factor of echo (tail components). min .. max attenuation'),
-    'GAMMA_ENL': (19, 17, 'float', 5, 0, 'rw', 'Over-subtraction factor of non-linear echo. min .. max attenuation'),
-    'NLATTENONOFF': (19, 18, 'int', 1, 0, 'rw', 'Non-Linear echo attenuation.', '0 = OFF', '1 = ON'),
-    'NLAEC_MODE': (19, 20, 'int', 2, 0, 'rw', 'Non-Linear AEC training mode.', '0 = OFF', '1 = ON - phase 1', '2 = ON - phase 2'),
-    'SPEECHDETECTED': (19, 22, 'int', 1, 0, 'ro', 'Speech detection status.', '0 = false (no speech detected)', '1 = true (speech detected)'),
-    'FSBUPDATED': (19, 23, 'int', 1, 0, 'ro', 'FSB Update Decision.', '0 = false (FSB was not updated)', '1 = true (FSB was updated)'),
-    'FSBPATHCHANGE': (19, 24, 'int', 1, 0, 'ro', 'FSB Path Change Detection.', '0 = false (no path change detected)', '1 = true (path change detected)'),
-    'TRANSIENTONOFF': (19, 29, 'int', 1, 0, 'rw', 'Transient echo suppression.', '0 = OFF', '1 = ON'),
-    'VOICEACTIVITY': (19, 32, 'int', 1, 0, 'ro', 'VAD voice activity status.', '0 = false (no voice activity)', '1 = true (voice activity)'),
-    'STATNOISEONOFF_SR': (19, 33, 'int', 1, 0, 'rw', 'Stationary noise suppression for ASR.', '0 = OFF', '1 = ON'),
-    'NONSTATNOISEONOFF_SR': (19, 34, 'int', 1, 0, 'rw', 'Non-stationary noise suppression for ASR.', '0 = OFF', '1 = ON'),
-    'GAMMA_NS_SR': (19, 35, 'float', 3, 0, 'rw', 'Over-subtraction factor of stationary noise for ASR. ', '[0.0 .. 3.0] (default: 1.0)'),
-    'GAMMA_NN_SR': (19, 36, 'float', 3, 0, 'rw', 'Over-subtraction factor of non-stationary noise for ASR. ', '[0.0 .. 3.0] (default: 1.1)'),
-    'MIN_NS_SR': (19, 37, 'float', 1, 0, 'rw', 'Gain-floor for stationary noise suppression for ASR.', '[−inf .. 0] dB (default: −16dB = 20log10(0.15))'),
-    'MIN_NN_SR': (19, 38, 'float', 1, 0, 'rw', 'Gain-floor for non-stationary noise suppression for ASR.', '[−inf .. 0] dB (default: −10dB = 20log10(0.3))'),
-    'GAMMAVAD_SR': (19, 39, 'float', 1000, 0, 'rw', 'Set the threshold for voice activity detection.', '[−inf .. 60] dB (default: 3.5dB 20log10(1.5))'),
-    # 'KEYWORDDETECT': (20, 0, 'int', 1, 0, 'ro', 'Keyword detected. Current value so needs polling.'),
-    'DOAANGLE': (21, 0, 'int', 359, 0, 'ro', 'DOA angle. Current value. Orientation depends on build configuration.')
-}
-
-
-class Tuning:
-    TIMEOUT = 100000
-
-    def __init__(self, dev):
-        self.dev = dev
-
-    def write(self, name, value):
-        try:
-            data = PARAMETERS[name]
-        except KeyError:
-            return
-
-        if data[5] == 'ro':
-            raise ValueError('{} is read-only'.format(name))
-
-        id = data[0]
-
-        # 4 bytes offset, 4 bytes value, 4 bytes type
-        if data[2] == 'int':
-            payload = struct.pack(b'iii', data[1], int(value), 1)
-        else:
-            payload = struct.pack(b'ifi', data[1], float(value), 0)
-
-        self.dev.ctrl_transfer(
-            usb.util.CTRL_OUT | usb.util.CTRL_TYPE_VENDOR | usb.util.CTRL_RECIPIENT_DEVICE,
-            0, 0, id, payload, self.TIMEOUT)
-
-    def read(self, name):
-        try:
-            data = PARAMETERS[name]
-        except KeyError:
-            return
-
-        id = data[0]
-
-        cmd = 0x80 | data[1]
-        if data[2] == 'int':
-            cmd |= 0x40
-
-        length = 8
-
-        response = self.dev.ctrl_transfer(
-            usb.util.CTRL_IN | usb.util.CTRL_TYPE_VENDOR | usb.util.CTRL_RECIPIENT_DEVICE,
-            0, cmd, id, length, self.TIMEOUT)
-
-        response = struct.unpack(b'ii', response.tostring())
-
-        if data[2] == 'int':
-            result = response[0]
-        else:
-            result = response[0] * (2.**response[1])
-
-        return result
-
-    def set_vad_threshold(self, db):
-        self.write('GAMMAVAD_SR', db)
-
-    def is_voice(self):
-        return self.read('VOICEACTIVITY')
-
-    @property
-    def direction(self):
-        return self.read('DOAANGLE')
-
-    @property
-    def version(self):
-        return self.dev.ctrl_transfer(
-            usb.util.CTRL_IN | usb.util.CTRL_TYPE_VENDOR | usb.util.CTRL_RECIPIENT_DEVICE,
-            0, 0x80, 0, 1, self.TIMEOUT)[0]
-
-    def close(self):
-        """
-        close the interface
-        """
-        usb.util.dispose_resources(self.dev)
-
-
-def find(vid=0x2886, pid=0x0018):
-    dev = usb.core.find(idVendor=vid, idProduct=pid)
-    if not dev:
-        return
-
-    # configuration = dev.get_active_configuration()
-
-    # interface_number = None
-    # for interface in configuration:
-    #     interface_number = interface.bInterfaceNumber
-
-    #     if dev.is_kernel_driver_active(interface_number):
-    #         dev.detach_kernel_driver(interface_number)
-
-    return Tuning(dev)
-
-
-
-def main():
-    if len(sys.argv) > 1:
-        if sys.argv[1] == '-p':
-            print('name\t\t\ttype\tmax\tmin\tr/w\tinfo')
-            print('-------------------------------')
-            for name in sorted(PARAMETERS.keys()):
-                data = PARAMETERS[name]
-                print('{:16}\t{}'.format(name, b'\t'.join([str(i) for i in data[2:7]])))
-                for extra in data[7:]:
-                    print('{}{}'.format(' '*60, extra))
-        else:
-            dev = find()
-            if not dev:
-                print('No device found')
-                sys.exit(1)
-
-            # print('version: {}'.format(dev.version))
-
-            if sys.argv[1] == '-r':
-                print('{:24} {}'.format('name', 'value'))
-                print('-------------------------------')
-                for name in sorted(PARAMETERS.keys()):
-                    print('{:24} {}'.format(name, dev.read(name)))
-            else:
-                name = sys.argv[1].upper()
-                if name in PARAMETERS:
-                    if len(sys.argv) > 2:
-                        dev.write(name, sys.argv[2])
-                    
-                    print('{}: {}'.format(name, dev.read(name)))
-                else:
-                    print('{} is not a valid name'.format(name))
-
-            dev.close()
-    else:
-        print(USAGE.format(sys.argv[0]))
-
-if __name__ == '__main__':
-    main()